New Robust Speech Recognition By Using Nonlinear Running Spectrurn Filter

Author

Hayasaka, Noboru ; Khankhavivone, Kham ; Miyanaga, Yoshikazu ; Songwatana, Kraisin

Author_Institution

Graduate Sch. of Inf. Sci. & Technonology, Hokkaido Univ., Sapporo

fYear

2006

fDate

Oct. 18 2006-Sept. 20 2006

Firstpage

133

Lastpage

136

Abstract

This report proposes new design of nonlinear running spectrum filters. The running spectrum filters have been applied for robust speech recognition. Using these filters, the system can recognize speech accurately in low SNR. However, when we consider high SNR circumstances, these filters interfere sometimes with accurate speech recognition. In this report, another approach on robust speech recognition is introduced as nonlinear running spectrum filtering (NRSF). This method can be used in various cases of low-high SNRs. It is shown in this report that the new NRSF can be used for robust speech recognition with high accuracy and low calculation cost

Keywords

filtering theory; speech recognition; nonlinear running spectrum filtering; robust speech recognition; speech analysis; Additive noise; Band pass filters; Cepstrum; Costs; Filtering; Finite impulse response filter; IIR filters; Low pass filters; Noise robustness; Speech recognition; DRA; Noise Robust Speech Analysis; RSF; Robust Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications and Information Technologies, 2006. ISCIT '06. International Symposium on

Conference_Location

Bangkok

Print_ISBN

0-7803-9741-X

Electronic_ISBN

0-7803-9741-X

Type

conf

DOI

10.1109/ISCIT.2006.339902

Filename

4141528